mirror of
https://github.com/Stone-Red-Code/dvc.git
synced 2026-11-10 07:18:27 +01:00
Peter Rowlands (변기호)
114a07e7a4
* objects.status: use object IDs instead of naive objects * objects.transfer: use object IDs instead of naive objects * objects: add ReferenceHashFile * odb: add ReferenceObjectDB * repo: collect used object IDs instead of naive objs * support basic/naive fs serialization * objects.stage: stage file objects in addition to trees * objects: remove save(), update transfer() * output/dep: update for osave removal * path_info: support both url and path attributes * status/gc: use object IDs instead of naive objs * diff: update staging usage * commit: update staging usage * tests: clean staging when needed * tests: update for save/transfer/stage changes * dvcfs: don't allow config serialization (repofs should be used instead) * utils: return mtime as str, size as int * tests: update unit tests for save/stage/transfer changes * objects: use Repo.open when needed in ReferenceHashFile * fix ls test staging * objects.stage: don't skip hash check when loading from state - individual hashes will still be loaded from state if they are still valid * ReferenceHashFile: serialize repo fs paths relative to repo root * preserve state when staging * objects.tree: skip hash computation in digest() when we have already loaded hash from state * always check file existence in referencehashfile * update repofs test since stage no longer allows nonexistent files * odb: only protect on check() if hash was verified * staging: use unique memfs namespace for staging per dest ODB * tests: clean full staging namespace * refodb: preserve repofs cache dir * repodependency: stage imports to local ODB and strict check circular imports * fetch: fetch staging last * staging: make dest odb mandatory and preserve state * refodb: cache nonlocal fs's * fix rebase errors * repofs: support full instantiation from fs config * repofs: preserve subrepo factory for erepos * tests: clarify repofs dirty file behavior
91 lines
2.2 KiB
Python
91 lines
2.2 KiB
Python
import errno
|
|
import logging
|
|
import os
|
|
from typing import TYPE_CHECKING, Optional
|
|
|
|
from .errors import ObjectFormatError
|
|
|
|
if TYPE_CHECKING:
|
|
from dvc.fs.base import BaseFileSystem
|
|
from dvc.hash_info import HashInfo
|
|
from dvc.types import AnyPath
|
|
|
|
from .db.base import ObjectDB
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class HashFile:
|
|
def __init__(
|
|
self,
|
|
path_info: Optional["AnyPath"],
|
|
fs: Optional["BaseFileSystem"],
|
|
hash_info: "HashInfo",
|
|
name: Optional[str] = None,
|
|
):
|
|
self.path_info = path_info
|
|
self.fs = fs
|
|
self.hash_info = hash_info
|
|
self.name = name
|
|
|
|
@property
|
|
def size(self):
|
|
return self.hash_info.size
|
|
|
|
def __len__(self):
|
|
return 1
|
|
|
|
def __str__(self):
|
|
return f"object {self.hash_info}"
|
|
|
|
def __bool__(self):
|
|
return bool(self.hash_info)
|
|
|
|
def __eq__(self, other):
|
|
if not isinstance(other, HashFile):
|
|
return False
|
|
return (
|
|
self.path_info == other.path_info
|
|
and self.fs == other.fs
|
|
and self.hash_info == other.hash_info
|
|
)
|
|
|
|
def __hash__(self):
|
|
return hash(
|
|
(
|
|
self.hash_info,
|
|
self.path_info,
|
|
self.fs.scheme if self.fs else None,
|
|
)
|
|
)
|
|
|
|
def check(self, odb: "ObjectDB", check_hash: bool = True):
|
|
if not check_hash:
|
|
assert self.fs
|
|
if not self.fs.exists(self.path_info):
|
|
raise FileNotFoundError(
|
|
errno.ENOENT, os.strerror(errno.ENOENT), self.path_info
|
|
)
|
|
else:
|
|
return None
|
|
|
|
self._check_hash(odb)
|
|
|
|
def _check_hash(self, odb):
|
|
from .stage import get_file_hash
|
|
|
|
actual = get_file_hash(
|
|
self.path_info, self.fs, self.hash_info.name, odb.state
|
|
)
|
|
|
|
logger.trace(
|
|
"cache '%s' expected '%s' actual '%s'",
|
|
self.path_info,
|
|
self.hash_info,
|
|
actual,
|
|
)
|
|
|
|
assert actual.name == self.hash_info.name
|
|
if actual.value.split(".")[0] != self.hash_info.value.split(".")[0]:
|
|
raise ObjectFormatError(f"{self} is corrupted")
|